Data Visualization

import pandas as pd
import math
import numpy as np
import numpy as np
import pandas as pd
import shapefile as shp
import matplotlib.pyplot as plt
import seaborn as sns
from cancerolstools import preprocess as pp
from cancerolstools import visuals as vi

fips_df = pp.import_fips()
cancer_df = pp.import_cancer()

cancer_df = pp.cancer_preprocess(cancer_df)
cancer_df = pp.merge_data(cancer_df, fips_df)

graphdata = pp.graph_dataframe(cancer_df)
graphdata

	fips	anomalies
0	53035	0.000000
1	53037	0.000000
2	53039	0.000000
3	16061	0.000000
4	21135	0.000000
...	...	...
14223	48159	0.000000
14224	50011	0.000000
14225	51067	0.000000
14226	53021	0.000000
14227	20061	1.140201

14228 rows × 2 columns

from urllib.request import urlopen
import json
with urlopen('https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json') as response:
    counties = json.load(response)

import plotly.express as px


fig = vi.anomaly_map(graphdata)
fig.show()
# fig = px.choropleth_mapbox(newbieLOG, geojson=counties, locations='fips', color='anomalies',
#                            color_continuous_scale="Hot_r",
#                            range_color=(0, 4),
#                            mapbox_style="carto-positron",
#                            zoom=3, center = {"lat": 37.0902, "lon": -95.7129},
#                            opacity=0.5,
#                            labels={'unemp':'unemployment rate'}
#                           )
# fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
# fig.show()

import pandas as pd
import matplotlib.pyplot as plt
import plotly.graph_objects as go

# df_race = cancer_df[['TARGET_deathRate', 'medIncome', 'PctWhite', 'PctBlack', 'PctAsian', 'PctOtherRace']]
# df_race = df_race.melt(id_vars=['TARGET_deathRate', 'medIncome'], var_name='variable')

# def get_variable_group(variable):
#     if variable == 'pctwhite':
#         return 'White'
#     elif variable == 'pctblack':
#         return 'Black'
#     elif variable == 'pctasian':
#         return 'Asian'
#     else:
#         return 'Other'

# df_race['variable_group'] = df_race['variable'].apply(get_variable_group)

race_plot_df = vi.df_race(cancer_df)

# colors = ['red', 'blue', 'green', 'purple']
# color_map = dict(zip(df_race['variable_group'].unique(), colors))

# fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(12, 12))
# for ax, variable in zip(axes.flatten(), df_race['variable'].unique()):
#     data = df_race[df_race['variable'] == variable]
#     ax.scatter(data['value'], data['TARGET_deathRate'], c=data['variable_group'].apply(lambda x: color_map[x]), s=data['medIncome']/5000, alpha=0.7)
#     ax.set_xlabel('Percentage of population by race')
#     ax.set_ylabel('Target death rate')
#     ax.set_title(variable)
#     ax.set_ylim([100, 400])

fig = vi.race_income_plot(race_plot_df)

plt.suptitle('Impact of race and income on target death rate', fontsize=16)
plt.tight_layout()
plt.subplots_adjust(top=0.92)
plt.show()